fix: close Chromium tabs on crawler fetch error paths

new_page() opened a tab that was only closed on the happy path; a `?` on
wait_for_nav / content() leaked it (chromiumoxide doesn't close on drop),
so errored fetches accumulated tabs in the shared browser. Add a generic,
unit-tested `close_after(close, body)` helper and wrap the three fetch
sites (chapter content, session probe, source navigate) so the tab is
closed on every exit path — including navigate's content()-read branch,
which previously leaked.

Bump to 0.124.5.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-07-07 21:04:50 +02:00
parent b7d8faadf7
commit 46134c8760
7 changed files with 136 additions and 53 deletions

View File

@@ -122,22 +122,31 @@ async fn fetch_chapter_html_once(
.new_page(source_url)
.await
.with_context(|| format!("open chapter page {source_url}"))?;
crate::crawler::nav::wait_for_nav(&page)
.await
.context("wait for chapter nav")?;
// Best-effort wait for the reader marker — same partial-render
// race that bit the chapter-list parser can hit here. Timeout is
// not an error; the chapter probe + parser sentinels still catch
// real failures.
let _ = crate::crawler::nav::wait_for_selector(
&page,
"a#pic_container",
crate::crawler::nav::SELECTOR_TIMEOUT,
// Close the tab on every exit path — a `?` on wait_for_nav / content()
// would otherwise leak it (chromiumoxide doesn't close on drop).
let closer = page.clone();
crate::crawler::nav::close_after(
async move {
closer.close().await.ok();
},
async {
crate::crawler::nav::wait_for_nav(&page)
.await
.context("wait for chapter nav")?;
// Best-effort wait for the reader marker — same partial-render
// race that bit the chapter-list parser can hit here. Timeout is
// not an error; the chapter probe + parser sentinels still catch
// real failures.
let _ = crate::crawler::nav::wait_for_selector(
&page,
"a#pic_container",
crate::crawler::nav::SELECTOR_TIMEOUT,
)
.await;
page.content().await.context("read chapter html")
},
)
.await;
let html = page.content().await.context("read chapter html")?;
page.close().await.ok();
Ok(html)
.await
}
/// Pure-over-IO loop: fetch + classify, up to `max_attempts` total